Source |
HackRead |
Identifiant |
8646597 |
Date de publication |
2025-02-03 16:28:01 (vue: 2025-02-03 17:08:08) |
Titre |
Cisco Finds DeepSeek R1 Highly Vulnerable to Harmful Prompts |
Texte |
DeepSeek R1, a cost-efficient AI model, achieves impressive reasoning but fails all safety tests in a new study…
DeepSeek R1, a cost-efficient AI model, achieves impressive reasoning but fails all safety tests in a new study… |
Notes |
★★★
|
Envoyé |
Oui |
Condensat |
achieves all but cisco cost deepseek efficient fails finds harmful highly impressive model new prompts reasoning safety study… tests vulnerable |
Tags |
|
Stories |
|
Move |
|